Prediksi Skor Pertandingan Sepak Bola menggunakan Neuroevolution of Augmenting Topologies dan Backpropagation

Welly Winata, Lily Puspa Dewi, Alvin Nathaniel Tjondrowiguno

Abstract


Football, or soccer is the most popular sport in the world. What
makes football special is the uncertainty and unpredictable result.
There are a lot of factors that can affect the result of a football
match, such as strategy, skill, or even luck. Therefore, predicting
the outcome of football match can be challenging yet interesting
task.
This research started with neuroevolution of augmenting
topologies, which useful to find the structur of a neural network.
Then, the network produced by NEAT is optimized using
backpropagation. Player ratings, team ratings, and player
position are used as features of neural network.
The hightest accuracies achieved are 81.5% on the final result
predicting, and 48% on score predicting, were obtained through
NEAT network that optimized by backpropagation, with player
ratings, team ratings, and total position from each sectors are
used as features.
However, on real life test, the player and team ratings are
unknown. To calculate the player and team ratings, averages
methods are used. Unfortunately, the network performed poorly
causing the accuracies to dropped significantly. Lack of
consistency from player ratings are believed to be the main
problem on calculating the player and team ratings.


Keywords


Machine Learning; Artificial Neural Network; Neuroevolution; Neuroevolution of Augmenting Topologies; Backpropagation

Full Text:

PDF

References


Aggarwal, C, C. 2018. Neural Networks and Deep Learning:

A Textbook. Cham: Springer Nature.

Boudway, I. 2018. Soccer Is the World’s Most Popular Sport

and Still Growing. URI=

https://www.bloomberg.com/news/articles/2018-06-

/soccer-is-the-world-s-most-popular-sport-and-stillgrowing.

Brownlee, J. 2017. How to One Hot Encode Sequence Data

in Python. URI=https://machinelearningmastery.com/how-toone-

hot-encode-sequence-data-in-python/.

Chen, D., Giles, C., Sun, G., Chen, H., Lee, Y., & Goudreau,

M. 1993. Constructive learning of recurrent neural networks.

IEEE International Conference on Neural Networks,.

Igiri, C. 2015. Support Vector Machine–Based Prediction

System for a Football Match Result. IOSR Journal of

Computer Engineering (IOSR-JCE), 21-26.

Morse, G., & Stanley, K. 2016. Simple Evolutionary

Optimization Can Rival Stochastic Gradient Descent in

Neural Networks. 2016 Proceedings of the on Genetic and

Evolutionary Computation Conference - GECCO '16.

Negnevitsky, M. 2005. Artificial Intelligence A Guide to

Intelligent System. Addison-Wesley Publishing Company,

Inc.

Pappalardo, L., & Cintia, P. 2018. Quantifying the relation

between performance and success in soccer. Advances in

Complex Systems,

Simeone, O. 2018. A Very Brief Introduction to Machine

Learning With Applications to Communication Systems.

IEEE Transactions on Cognitive Communications and

Networking, 648-664.

Stanley, K., & Miikkulainen, R. 2002. Evolving Neural

Networks through Augmenting Topologies. Evolutionary

Computation.


Refbacks

  • There are currently no refbacks.


Jurnal telah terindeks oleh :